website: https://www.chrisbail.net
github: https://github.com/cbail
Twitter: https://www.twitter.com/chris_bail

install.packages("rvest")
library(rvest)

We are going to begin by scraping this very simple web page from Wikipedia.

wikipedia_page<-read_html("https://en.wikipedia.org/wiki/World_Health_Organization_ranking_of_health_systems_in_2000")

wikipedia_page

{xml_document}
<html class="client-nojs" lang="en" dir="ltr">
[1] <head>\n<meta http-equiv="Content-Type" content="text/html; charset= ...
[2] <body class="mediawiki ltr sitedir-ltr mw-hide-empty-elt ns-0 ns-sub ...

section_of_wikipedia<-html_node(wikipedia_page, xpath='//*[@id="mw-content-text"]/div/table')
head(section_of_wikipedia)

$node
<pointer: 0x7f7f99da9740>

$doc
<pointer: 0x7f7f99d9a390>

health_rankings<-html_table(section_of_wikipedia)
head(health_rankings[,(1:2)])

              Country Attainment of goals / Health / Level (DALE)
1         Afghanistan                                         168
2             Albania                                         102
3             Algeria                                          84
4             Andorra                                          10
5              Angola                                         165
6 Antigua and Barbuda                                          48

http://selectorgadget.com/

duke_page<-read_html("https://www.duke.edu")
duke_events<-html_nodes(duke_page, css="li:nth-child(1) .epsilon")
html_text(duke_events)

[1] "In Appalachia, the Fight Against Opioid Abuse Comes to the Pulpit\n\n\t\t\t\t\t\t\t"
[2] "Get Started with Get Moving\n\n\t\t\t\t\t\t\t"                                      
[3] "Duke Hospital Exhibit: Meet the Artist & Demonstration with painter Sally Sutton"   
[4] "Nicholas School Students Speak Out on Inclusion"                                    

devtools::install_github("ropensci/RSelenium")
library(Rselenium)

Note: you may need to install Java to get up and running see this tutorial

rD <- rsDriver()
remDr <- rD$client

remDr$navigate("https://www.duke.edu")

search_box <- remDr$findElement(using = 'css selector', 'fieldset input')

search_box$sendKeysToElement(list("data science", "\uE007"))

#create list of websites to scrape
my_list_of_websites<-c("www.duke.edu","www.penn.edu")

#create place to store text data
text_data<-as.data.frame(NULL)

#loop
for(i in 1: length(my_list_of_websites)){

  #read in page and extract text
  page<-read_html("https://www.duke.edu")
  events<-html_nodes(page, css="li:nth-child(1) .epsilon")
  text<-html_text(events)

  #store text in dataset created above
  text_data<-rbind(text_data,text)

  #print iteration for de-bugging
  print(i)
}